[PATCH v13 4/4] PM / Domains: Add genpd governor for CPUs

[Ulf Hansson]

As it's now perfectly possible that a PM domain managed by genpd contains
devices belonging to CPUs, we should start to take into account the
residency values for the idle states during the state selection process.
The residency value specifies the minimum duration of time, the CPU or a
group of CPUs, needs to spend in an idle state to not waste energy entering
it.

To deal with this, let's add a new genpd governor, pm_domain_cpu_gov, that
may be used for a PM domain that have CPU devices attached or if the CPUs
are attached through subdomains.

The new governor computes the minimum expected idle duration time for the
online CPUs being attached to the PM domain and its subdomains. Then in the
state selection process, trying the deepest state first, it verifies that
the idle duration time satisfies the state's residency value.

It should be noted that, when computing the minimum expected idle duration
time, we use the information about the next timer/tick that is stored in
the per CPU variable, cpuidle_devices, for the related CPUs. Future wise,
this deserves to be improved, as there are obviously more reasons to why a
CPU may be woken up from idle.

Cc: Lina Iyer <ilina@xxxxxxxxxxxxxx>
Co-developed-by: Lina Iyer <lina.iyer@xxxxxxxxxx>
Acked-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Signed-off-by: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
---

Changes in v13:
	- As suggested by Rafael, use READ_ONCE when reading the next_hrtimer
	variable.

---
 drivers/base/power/domain_governor.c | 65 +++++++++++++++++++++++++++-
 include/linux/pm_domain.h            |  3 ++
 2 files changed, 67 insertions(+), 1 deletion(-)

diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 4d07e38a8247..7f9b80f46b3a 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -10,6 +10,9 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
 #include <linux/hrtimer.h>
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/ktime.h>
 
 static int dev_update_qos_constraint(struct device *dev, void *data)
 {
@@ -210,8 +213,10 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
 	struct gpd_link *link;
 
-	if (!genpd->max_off_time_changed)
+	if (!genpd->max_off_time_changed) {
+		genpd->state_idx = genpd->cached_power_down_state_idx;
 		return genpd->cached_power_down_ok;
+	}
 
 	/*
 	 * We have to invalidate the cached results for the masters, so
@@ -236,6 +241,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		genpd->state_idx--;
 	}
 
+	genpd->cached_power_down_state_idx = genpd->state_idx;
 	return genpd->cached_power_down_ok;
 }
 
@@ -244,6 +250,58 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 	return false;
 }
 
+static bool cpu_power_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct cpuidle_device *dev;
+	ktime_t domain_wakeup, next_hrtimer;
+	s64 idle_duration_ns;
+	int cpu, i;
+
+	/* Validate dev PM QoS constraints. */
+	if (!default_power_down_ok(pd))
+		return false;
+
+	if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
+		return true;
+
+	/*
+	 * Find the next wakeup for any of the online CPUs within the PM domain
+	 * and its subdomains. Note, we only need the genpd->cpus, as it already
+	 * contains a mask of all CPUs from subdomains.
+	 */
+	domain_wakeup = ktime_set(KTIME_SEC_MAX, 0);
+	for_each_cpu_and(cpu, genpd->cpus, cpu_online_mask) {
+		dev = per_cpu(cpuidle_devices, cpu);
+		if (dev) {
+			next_hrtimer = READ_ONCE(dev->next_hrtimer);
+			if (ktime_before(next_hrtimer, domain_wakeup))
+				domain_wakeup = next_hrtimer;
+		}
+	}
+
+	/* The minimum idle duration is from now - until the next wakeup. */
+	idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get()));
+	if (idle_duration_ns <= 0)
+		return false;
+
+	/*
+	 * Find the deepest idle state that has its residency value satisfied
+	 * and by also taking into account the power off latency for the state.
+	 * Start at the state picked by the dev PM QoS constraint validation.
+	 */
+	i = genpd->state_idx;
+	do {
+		if (idle_duration_ns >= (genpd->states[i].residency_ns +
+		    genpd->states[i].power_off_latency_ns)) {
+			genpd->state_idx = i;
+			return true;
+		}
+	} while (--i >= 0);
+
+	return false;
+}
+
 struct dev_power_governor simple_qos_governor = {
 	.suspend_ok = default_suspend_ok,
 	.power_down_ok = default_power_down_ok,
@@ -256,3 +314,8 @@ struct dev_power_governor pm_domain_always_on_gov = {
 	.power_down_ok = always_on_power_down_ok,
 	.suspend_ok = default_suspend_ok,
 };
+
+struct dev_power_governor pm_domain_cpu_gov = {
+	.suspend_ok = default_suspend_ok,
+	.power_down_ok = cpu_power_down_ok,
+};
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index a6e251fe9deb..ae7061556a26 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -118,6 +118,7 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
+	bool cached_power_down_state_idx;
 	int (*attach_dev)(struct generic_pm_domain *domain,
 			  struct device *dev);
 	void (*detach_dev)(struct generic_pm_domain *domain,
@@ -202,6 +203,7 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
+extern struct dev_power_governor pm_domain_cpu_gov;
 #else
 
 static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
@@ -245,6 +247,7 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev,
 
 #define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
 #define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
+#define pm_domain_cpu_gov		(*(struct dev_power_governor *)(NULL))
 #endif
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
-- 
2.17.1